DART Monthly Webinar // Learning-based Approaches to Data-driven Predictions

Title: Learning-based Approaches to Data-driven Predictions
Presenter(s): Md Karim, Olcay Kursun, Xiao Liu, Chase Rainwater, and Shengfan Zhang
Date presented: April 28, 2021

A major challenge in building secure and widely adopted deep learning systems is that they sometimes make wrong, unexplainable, and/or unpredictable misclassifications. This talk overviews initial efforts towards techniques using large-scale deep learning with multi-source integrated data sets. In addition, we introduce the integration of statistical learning approaches with learning-based frameworks.

Webinar FAQs:

    Presenter's Bios:

    Dr. MD Karim earned his Ph.D. in Computer Science from the University of Louisiana at Lafayette. He is a Professor of Computer Science and the Chair of the Department of Mathematics and Computer Science at the Southern Arkansas University. He also serves as the Director of the Computer Science graduate program. In the past, he was a researcher at the Center for Secure Cyberspace at the Louisiana Tech University. His research interests include cyber security, deep reinforcement learning, and causal interpretation. He worked on various research projects sponsored by DARPA, AFOSR, AFRL, and NASA. He is currently a co-lead in an NSF EPSCoR project on data analytics.

    Dr. Olcay Kursun received his PhD degree in 2004 in Computer Science from the University of Central Florida on developing cortex-inspired neural networks. He worked for Istanbul University as associate professor until 2016. After more than a decade of international collaboration, in 2016, he joined his collaborators' neuroscience lab in the Department of Biomedical Engineering at the University of North Carolina, Chapel Hill, where he continued developing machine learning and computational neuroscience algorithms. Since Fall 2017, he is a faculty member in the Department of Computer Science at the University of Central Arkansas, where he has co-founded the Intelligent and Embedded Systems lab. His research interests are in the field of machine learning and pattern recognition with particular interest in deep learning, multiview machine learning, biological neural models and their applications in neuroscience, biomedical engineering, and embedded systems.

    Dr. Xiao Liu is an Assistant Professor at the Department of Industrial Engineering, University of Arkansas. Before that, he held permanent research scientist positions at IBM Thomas J. Watson Research Center (2015~2017), and IBM Smarter Cities Research Collaboratory Singapore (2012~2015). From 2013 to 2016, he also served as an Adjunct Assistant Professor at the ISE Department, National University of Singapore. Dr. Liu’s research focuses on engineering-knowledge-based data-driven methodologies, including PDE-based spatiotemporal models for physical convection-diffusion processes, integration of engineering domain knowledge with sensor data for monitoring complex engineered systems, and tree-based ensemble statistical learning for recurrent event data. Dr. Liu’s research outcomes have been published on journals in both Industrial Engineering and Applied Statistics, and have been recognized with the SPES award (2018) by the American Statistical Association and the IBM Outstanding Technical Achievement award (2015 and 2017) by the IBM research division. Dr. Liu is the president-elect of the Data Analytics & Information Systems Division at the Institute of Industrial and Systems Engineers (IISE).

    Dr. Chase Rainwater joined the industrial engineering faculty at the University of Arkansas in August 2009 where he is currently an Associate Professor and serves as Associate Department Head. He is the Director of the J.B. Hunt Innovation Center of Excellence and the Co-Director of the Arkansas Security Research and Education Institute. His contributions to industrial engineering research include more than 30 published journal articles, conference papers and book chapters. Dr. Rainwater's research interests include supply chain logistics, national security, large-scale algorithm design and food safety. He has advised 6 Ph.D. dissertations along with multiple M.S. and undergraduate theses. He is an active member in the Institute for Operations Research and Management Sciences and served as Program Chair for the 2018 Industrial and Systems Engineering Research Conference. Dr. Rainwater serves on numerous departmental and college committees and is active in the Northwest Arkansas STEM community as a 10-year mentor in the FIRST robotics program. Dr. Rainwater was awarded the University of Arkansas Industrial Engineering Outstanding Teaching Award in 2012, 2014 and 2015, the Outstanding Industrial Engineering Faculty Member in 2017, the College of Engineering Collaborative Research Faculty Award in 2018 and the University of Arkansas Industrial Engineering Outstanding Research Award in 2019.

    Dr. Shengfan Zhang is an Associate Professor and 2021-2022 John L. Imhoff Chair in the Department of Industrial Engineering at the University of Arkansas. She received her Ph.D. and M.S. in Industrial Engineering from North Carolina State University. Zhang’s current research focuses on developing methodologies and solution approaches in medical decision making, especially advancing predictive and prescriptive analytics for disease prevention and treatment. Her research is funded by the National Institute of Health, National Science Foundation, Department of Transportation, Arkansas Biosciences Institute, etc. She and her student co-authors have won several awards and recognition, including the IISE Best Paper Award in Track and the INFORMS Interactive Sessions Competition. Zhang is currently an Area Editor for the journal Health Systems and Associate Editor for IISE Transactions on Healthcare Systems Engineering. She is serving as the Past President for the INFORMS Section on Public Sector Operations Research, and a member of the Diversity, Equity, and Inclusion Committee of INFORMS.